[pypy-svn] r30546 - pypy/dist/pypy/module/rctime
rhymes at codespeak.net
rhymes at codespeak.net
Tue Jul 25 22:29:10 CEST 2006
Author: rhymes
Date: Tue Jul 25 22:29:00 2006
New Revision: 30546
Added:
pypy/dist/pypy/module/rctime/strptime.txt
Log:
added strptime.txt: it contains the code removed from the module
Added: pypy/dist/pypy/module/rctime/strptime.txt
==============================================================================
--- (empty file)
+++ pypy/dist/pypy/module/rctime/strptime.txt Tue Jul 25 22:29:00 2006
@@ -0,0 +1,1321 @@
+libc.setlocale.argtype = [c_int, c_char_p]
+libc.setlocale.restype = c_char_p
+
+def strptime(space, w_string, w_format="%a %b %d %H:%M:%S %Y"):
+ """strptime(string, format) -> struct_time
+
+ Parse a string to a time tuple according to a format specification.
+ See the library reference manual for formatting codes
+ (same as strftime())."""
+
+ string = space.str_w(w_string)
+ format = space.str_w(w_format)
+
+ return _strptime(space, string, format)
+strptime.unwrap_spec = [ObjSpace, W_Root, W_Root]
+
+"""Strptime-related classes and functions.
+
+CLASSES:
+ LocaleTime -- Discovers and stores locale-specific time information
+ TimeRE -- Creates regexes for pattern matching a string of text containing
+ time information
+
+FUNCTIONS:
+ _getlang -- Figure out what language is being used for the locale
+ strptime -- Calculates the time struct represented by the passed-in string
+
+"""
+from locale import LC_ALL, LC_TIME
+import calendar
+from re import compile as re_compile
+from re import IGNORECASE
+from re import escape as re_escape
+from datetime import date as datetime_date
+import encodings
+
+# "backported" some stuff from locale.py and _localemodule.c to make it translate
+def _setlocale(space, category):
+ res = libc.setlocale(category, None)
+ if not res:
+ raise OperationError(space.w_Error, space.wrap("locale query failed"))
+ return space.wrap(res)
+
+locale_encoding_alias = {
+
+ # Mappings for non-standard encoding names used in locale names
+ '437': 'C',
+ 'c': 'C',
+ 'en': 'ISO8859-1',
+ 'jis': 'JIS7',
+ 'jis7': 'JIS7',
+ 'ajec': 'eucJP',
+
+ # Mappings from Python codec names to C lib encoding names
+ 'ascii': 'ISO8859-1',
+ 'latin_1': 'ISO8859-1',
+ 'iso8859_1': 'ISO8859-1',
+ 'iso8859_10': 'ISO8859-10',
+ 'iso8859_11': 'ISO8859-11',
+ 'iso8859_13': 'ISO8859-13',
+ 'iso8859_14': 'ISO8859-14',
+ 'iso8859_15': 'ISO8859-15',
+ 'iso8859_2': 'ISO8859-2',
+ 'iso8859_3': 'ISO8859-3',
+ 'iso8859_4': 'ISO8859-4',
+ 'iso8859_5': 'ISO8859-5',
+ 'iso8859_6': 'ISO8859-6',
+ 'iso8859_7': 'ISO8859-7',
+ 'iso8859_8': 'ISO8859-8',
+ 'iso8859_9': 'ISO8859-9',
+ 'iso2022_jp': 'JIS7',
+ 'shift_jis': 'SJIS',
+ 'tactis': 'TACTIS',
+ 'euc_jp': 'eucJP',
+ 'euc_kr': 'eucKR',
+ 'utf_8': 'UTF8',
+ 'koi8_r': 'KOI8-R',
+ 'koi8_u': 'KOI8-U',
+ # XXX This list is still incomplete. If you know more
+ # mappings, please file a bug report. Thanks.
+}
+
+locale_alias = {
+ 'a3': 'a3_AZ.KOI8-C',
+ 'a3_az': 'a3_AZ.KOI8-C',
+ 'a3_az.koi8c': 'a3_AZ.KOI8-C',
+ 'af': 'af_ZA.ISO8859-1',
+ 'af_za': 'af_ZA.ISO8859-1',
+ 'af_za.iso88591': 'af_ZA.ISO8859-1',
+ 'am': 'am_ET.UTF-8',
+ 'american': 'en_US.ISO8859-1',
+ 'american.iso88591': 'en_US.ISO8859-1',
+ 'ar': 'ar_AA.ISO8859-6',
+ 'ar_aa': 'ar_AA.ISO8859-6',
+ 'ar_aa.iso88596': 'ar_AA.ISO8859-6',
+ 'ar_ae': 'ar_AE.ISO8859-6',
+ 'ar_bh': 'ar_BH.ISO8859-6',
+ 'ar_dz': 'ar_DZ.ISO8859-6',
+ 'ar_eg': 'ar_EG.ISO8859-6',
+ 'ar_eg.iso88596': 'ar_EG.ISO8859-6',
+ 'ar_iq': 'ar_IQ.ISO8859-6',
+ 'ar_jo': 'ar_JO.ISO8859-6',
+ 'ar_kw': 'ar_KW.ISO8859-6',
+ 'ar_lb': 'ar_LB.ISO8859-6',
+ 'ar_ly': 'ar_LY.ISO8859-6',
+ 'ar_ma': 'ar_MA.ISO8859-6',
+ 'ar_om': 'ar_OM.ISO8859-6',
+ 'ar_qa': 'ar_QA.ISO8859-6',
+ 'ar_sa': 'ar_SA.ISO8859-6',
+ 'ar_sa.iso88596': 'ar_SA.ISO8859-6',
+ 'ar_sd': 'ar_SD.ISO8859-6',
+ 'ar_sy': 'ar_SY.ISO8859-6',
+ 'ar_tn': 'ar_TN.ISO8859-6',
+ 'ar_ye': 'ar_YE.ISO8859-6',
+ 'arabic': 'ar_AA.ISO8859-6',
+ 'arabic.iso88596': 'ar_AA.ISO8859-6',
+ 'az': 'az_AZ.ISO8859-9E',
+ 'az_az': 'az_AZ.ISO8859-9E',
+ 'az_az.iso88599e': 'az_AZ.ISO8859-9E',
+ 'be': 'be_BY.CP1251',
+ 'be_by': 'be_BY.CP1251',
+ 'be_by.cp1251': 'be_BY.CP1251',
+ 'be_by.microsoftcp1251': 'be_BY.CP1251',
+ 'bg': 'bg_BG.CP1251',
+ 'bg_bg': 'bg_BG.CP1251',
+ 'bg_bg.cp1251': 'bg_BG.CP1251',
+ 'bg_bg.iso88595': 'bg_BG.ISO8859-5',
+ 'bg_bg.koi8r': 'bg_BG.KOI8-R',
+ 'bg_bg.microsoftcp1251': 'bg_BG.CP1251',
+ 'bokmal': 'nb_NO.ISO8859-1',
+ 'bokm\xe5l': 'nb_NO.ISO8859-1',
+ 'br': 'br_FR.ISO8859-1',
+ 'br_fr': 'br_FR.ISO8859-1',
+ 'br_fr.iso88591': 'br_FR.ISO8859-1',
+ 'br_fr.iso885914': 'br_FR.ISO8859-14',
+ 'br_fr.iso885915': 'br_FR.ISO8859-15',
+ 'br_fr at euro': 'br_FR.ISO8859-15',
+ 'bulgarian': 'bg_BG.CP1251',
+ 'c': 'C',
+ 'c-french': 'fr_CA.ISO8859-1',
+ 'c-french.iso88591': 'fr_CA.ISO8859-1',
+ 'c.en': 'C',
+ 'c.iso88591': 'en_US.ISO8859-1',
+ 'c_c': 'C',
+ 'c_c.c': 'C',
+ 'ca': 'ca_ES.ISO8859-1',
+ 'ca_es': 'ca_ES.ISO8859-1',
+ 'ca_es.iso88591': 'ca_ES.ISO8859-1',
+ 'ca_es.iso885915': 'ca_ES.ISO8859-15',
+ 'ca_es at euro': 'ca_ES.ISO8859-15',
+ 'catalan': 'ca_ES.ISO8859-1',
+ 'cextend': 'en_US.ISO8859-1',
+ 'cextend.en': 'en_US.ISO8859-1',
+ 'chinese-s': 'zh_CN.eucCN',
+ 'chinese-t': 'zh_TW.eucTW',
+ 'croatian': 'hr_HR.ISO8859-2',
+ 'cs': 'cs_CZ.ISO8859-2',
+ 'cs_cs': 'cs_CZ.ISO8859-2',
+ 'cs_cs.iso88592': 'cs_CZ.ISO8859-2',
+ 'cs_cz': 'cs_CZ.ISO8859-2',
+ 'cs_cz.iso88592': 'cs_CZ.ISO8859-2',
+ 'cy': 'cy_GB.ISO8859-1',
+ 'cy_gb': 'cy_GB.ISO8859-1',
+ 'cy_gb.iso88591': 'cy_GB.ISO8859-1',
+ 'cy_gb.iso885914': 'cy_GB.ISO8859-14',
+ 'cy_gb.iso885915': 'cy_GB.ISO8859-15',
+ 'cy_gb at euro': 'cy_GB.ISO8859-15',
+ 'cz': 'cs_CZ.ISO8859-2',
+ 'cz_cz': 'cs_CZ.ISO8859-2',
+ 'czech': 'cs_CZ.ISO8859-2',
+ 'da': 'da_DK.ISO8859-1',
+ 'da_dk': 'da_DK.ISO8859-1',
+ 'da_dk.88591': 'da_DK.ISO8859-1',
+ 'da_dk.885915': 'da_DK.ISO8859-15',
+ 'da_dk.iso88591': 'da_DK.ISO8859-1',
+ 'da_dk.iso885915': 'da_DK.ISO8859-15',
+ 'da_dk at euro': 'da_DK.ISO8859-15',
+ 'danish': 'da_DK.ISO8859-1',
+ 'danish.iso88591': 'da_DK.ISO8859-1',
+ 'dansk': 'da_DK.ISO8859-1',
+ 'de': 'de_DE.ISO8859-1',
+ 'de_at': 'de_AT.ISO8859-1',
+ 'de_at.iso88591': 'de_AT.ISO8859-1',
+ 'de_at.iso885915': 'de_AT.ISO8859-15',
+ 'de_at at euro': 'de_AT.ISO8859-15',
+ 'de_be': 'de_BE.ISO8859-1',
+ 'de_be.iso88591': 'de_BE.ISO8859-1',
+ 'de_be.iso885915': 'de_BE.ISO8859-15',
+ 'de_be at euro': 'de_BE.ISO8859-15',
+ 'de_ch': 'de_CH.ISO8859-1',
+ 'de_ch.iso88591': 'de_CH.ISO8859-1',
+ 'de_ch.iso885915': 'de_CH.ISO8859-15',
+ 'de_ch at euro': 'de_CH.ISO8859-15',
+ 'de_de': 'de_DE.ISO8859-1',
+ 'de_de.88591': 'de_DE.ISO8859-1',
+ 'de_de.885915': 'de_DE.ISO8859-15',
+ 'de_de.885915 at euro': 'de_DE.ISO8859-15',
+ 'de_de.iso88591': 'de_DE.ISO8859-1',
+ 'de_de.iso885915': 'de_DE.ISO8859-15',
+ 'de_de at euro': 'de_DE.ISO8859-15',
+ 'de_lu': 'de_LU.ISO8859-1',
+ 'de_lu.iso88591': 'de_LU.ISO8859-1',
+ 'de_lu.iso885915': 'de_LU.ISO8859-15',
+ 'de_lu at euro': 'de_LU.ISO8859-15',
+ 'deutsch': 'de_DE.ISO8859-1',
+ 'dutch': 'nl_NL.ISO8859-1',
+ 'dutch.iso88591': 'nl_BE.ISO8859-1',
+ 'ee': 'ee_EE.ISO8859-4',
+ 'ee_ee': 'ee_EE.ISO8859-4',
+ 'ee_ee.iso88594': 'ee_EE.ISO8859-4',
+ 'eesti': 'et_EE.ISO8859-1',
+ 'el': 'el_GR.ISO8859-7',
+ 'el_gr': 'el_GR.ISO8859-7',
+ 'el_gr.iso88597': 'el_GR.ISO8859-7',
+ 'el_gr at euro': 'el_GR.ISO8859-15',
+ 'en': 'en_US.ISO8859-1',
+ 'en.iso88591': 'en_US.ISO8859-1',
+ 'en_au': 'en_AU.ISO8859-1',
+ 'en_au.iso88591': 'en_AU.ISO8859-1',
+ 'en_be': 'en_BE.ISO8859-1',
+ 'en_be at euro': 'en_BE.ISO8859-15',
+ 'en_bw': 'en_BW.ISO8859-1',
+ 'en_ca': 'en_CA.ISO8859-1',
+ 'en_ca.iso88591': 'en_CA.ISO8859-1',
+ 'en_gb': 'en_GB.ISO8859-1',
+ 'en_gb.88591': 'en_GB.ISO8859-1',
+ 'en_gb.iso88591': 'en_GB.ISO8859-1',
+ 'en_gb.iso885915': 'en_GB.ISO8859-15',
+ 'en_gb at euro': 'en_GB.ISO8859-15',
+ 'en_hk': 'en_HK.ISO8859-1',
+ 'en_ie': 'en_IE.ISO8859-1',
+ 'en_ie.iso88591': 'en_IE.ISO8859-1',
+ 'en_ie.iso885915': 'en_IE.ISO8859-15',
+ 'en_ie at euro': 'en_IE.ISO8859-15',
+ 'en_in': 'en_IN.ISO8859-1',
+ 'en_nz': 'en_NZ.ISO8859-1',
+ 'en_nz.iso88591': 'en_NZ.ISO8859-1',
+ 'en_ph': 'en_PH.ISO8859-1',
+ 'en_sg': 'en_SG.ISO8859-1',
+ 'en_uk': 'en_GB.ISO8859-1',
+ 'en_us': 'en_US.ISO8859-1',
+ 'en_us.88591': 'en_US.ISO8859-1',
+ 'en_us.885915': 'en_US.ISO8859-15',
+ 'en_us.iso88591': 'en_US.ISO8859-1',
+ 'en_us.iso885915': 'en_US.ISO8859-15',
+ 'en_us.iso885915 at euro': 'en_US.ISO8859-15',
+ 'en_us at euro': 'en_US.ISO8859-15',
+ 'en_us at euro@euro': 'en_US.ISO8859-15',
+ 'en_za': 'en_ZA.ISO8859-1',
+ 'en_za.88591': 'en_ZA.ISO8859-1',
+ 'en_za.iso88591': 'en_ZA.ISO8859-1',
+ 'en_za.iso885915': 'en_ZA.ISO8859-15',
+ 'en_za at euro': 'en_ZA.ISO8859-15',
+ 'en_zw': 'en_ZW.ISO8859-1',
+ 'eng_gb': 'en_GB.ISO8859-1',
+ 'eng_gb.8859': 'en_GB.ISO8859-1',
+ 'english': 'en_EN.ISO8859-1',
+ 'english.iso88591': 'en_EN.ISO8859-1',
+ 'english_uk': 'en_GB.ISO8859-1',
+ 'english_uk.8859': 'en_GB.ISO8859-1',
+ 'english_united-states': 'en_US.ISO8859-1',
+ 'english_united-states.437': 'C',
+ 'english_us': 'en_US.ISO8859-1',
+ 'english_us.8859': 'en_US.ISO8859-1',
+ 'english_us.ascii': 'en_US.ISO8859-1',
+ 'eo': 'eo_XX.ISO8859-3',
+ 'eo_eo': 'eo_EO.ISO8859-3',
+ 'eo_eo.iso88593': 'eo_EO.ISO8859-3',
+ 'eo_xx': 'eo_XX.ISO8859-3',
+ 'eo_xx.iso88593': 'eo_XX.ISO8859-3',
+ 'es': 'es_ES.ISO8859-1',
+ 'es_ar': 'es_AR.ISO8859-1',
+ 'es_ar.iso88591': 'es_AR.ISO8859-1',
+ 'es_bo': 'es_BO.ISO8859-1',
+ 'es_bo.iso88591': 'es_BO.ISO8859-1',
+ 'es_cl': 'es_CL.ISO8859-1',
+ 'es_cl.iso88591': 'es_CL.ISO8859-1',
+ 'es_co': 'es_CO.ISO8859-1',
+ 'es_co.iso88591': 'es_CO.ISO8859-1',
+ 'es_cr': 'es_CR.ISO8859-1',
+ 'es_cr.iso88591': 'es_CR.ISO8859-1',
+ 'es_do': 'es_DO.ISO8859-1',
+ 'es_do.iso88591': 'es_DO.ISO8859-1',
+ 'es_ec': 'es_EC.ISO8859-1',
+ 'es_ec.iso88591': 'es_EC.ISO8859-1',
+ 'es_es': 'es_ES.ISO8859-1',
+ 'es_es.88591': 'es_ES.ISO8859-1',
+ 'es_es.iso88591': 'es_ES.ISO8859-1',
+ 'es_es.iso885915': 'es_ES.ISO8859-15',
+ 'es_es at euro': 'es_ES.ISO8859-15',
+ 'es_gt': 'es_GT.ISO8859-1',
+ 'es_gt.iso88591': 'es_GT.ISO8859-1',
+ 'es_hn': 'es_HN.ISO8859-1',
+ 'es_hn.iso88591': 'es_HN.ISO8859-1',
+ 'es_mx': 'es_MX.ISO8859-1',
+ 'es_mx.iso88591': 'es_MX.ISO8859-1',
+ 'es_ni': 'es_NI.ISO8859-1',
+ 'es_ni.iso88591': 'es_NI.ISO8859-1',
+ 'es_pa': 'es_PA.ISO8859-1',
+ 'es_pa.iso88591': 'es_PA.ISO8859-1',
+ 'es_pa.iso885915': 'es_PA.ISO8859-15',
+ 'es_pa at euro': 'es_PA.ISO8859-15',
+ 'es_pe': 'es_PE.ISO8859-1',
+ 'es_pe.iso88591': 'es_PE.ISO8859-1',
+ 'es_pe.iso885915': 'es_PE.ISO8859-15',
+ 'es_pe at euro': 'es_PE.ISO8859-15',
+ 'es_pr': 'es_PR.ISO8859-1',
+ 'es_pr.iso88591': 'es_PR.ISO8859-1',
+ 'es_py': 'es_PY.ISO8859-1',
+ 'es_py.iso88591': 'es_PY.ISO8859-1',
+ 'es_py.iso885915': 'es_PY.ISO8859-15',
+ 'es_py at euro': 'es_PY.ISO8859-15',
+ 'es_sv': 'es_SV.ISO8859-1',
+ 'es_sv.iso88591': 'es_SV.ISO8859-1',
+ 'es_sv.iso885915': 'es_SV.ISO8859-15',
+ 'es_sv at euro': 'es_SV.ISO8859-15',
+ 'es_us': 'es_US.ISO8859-1',
+ 'es_uy': 'es_UY.ISO8859-1',
+ 'es_uy.iso88591': 'es_UY.ISO8859-1',
+ 'es_uy.iso885915': 'es_UY.ISO8859-15',
+ 'es_uy at euro': 'es_UY.ISO8859-15',
+ 'es_ve': 'es_VE.ISO8859-1',
+ 'es_ve.iso88591': 'es_VE.ISO8859-1',
+ 'es_ve.iso885915': 'es_VE.ISO8859-15',
+ 'es_ve at euro': 'es_VE.ISO8859-15',
+ 'estonian': 'et_EE.ISO8859-1',
+ 'et': 'et_EE.ISO8859-15',
+ 'et_ee': 'et_EE.ISO8859-15',
+ 'et_ee.iso88591': 'et_EE.ISO8859-1',
+ 'et_ee.iso885913': 'et_EE.ISO8859-13',
+ 'et_ee.iso885915': 'et_EE.ISO8859-15',
+ 'et_ee.iso88594': 'et_EE.ISO8859-4',
+ 'et_ee at euro': 'et_EE.ISO8859-15',
+ 'eu': 'eu_ES.ISO8859-1',
+ 'eu_es': 'eu_ES.ISO8859-1',
+ 'eu_es.iso88591': 'eu_ES.ISO8859-1',
+ 'eu_es.iso885915': 'eu_ES.ISO8859-15',
+ 'eu_es at euro': 'eu_ES.ISO8859-15',
+ 'fa': 'fa_IR.UTF-8',
+ 'fa_ir': 'fa_IR.UTF-8',
+ 'fa_ir.isiri3342': 'fa_IR.ISIRI-3342',
+ 'fi': 'fi_FI.ISO8859-15',
+ 'fi_fi': 'fi_FI.ISO8859-15',
+ 'fi_fi.88591': 'fi_FI.ISO8859-1',
+ 'fi_fi.iso88591': 'fi_FI.ISO8859-1',
+ 'fi_fi.iso885915': 'fi_FI.ISO8859-15',
+ 'fi_fi.utf8 at euro': 'fi_FI.UTF-8',
+ 'fi_fi at euro': 'fi_FI.ISO8859-15',
+ 'finnish': 'fi_FI.ISO8859-1',
+ 'finnish.iso88591': 'fi_FI.ISO8859-1',
+ 'fo': 'fo_FO.ISO8859-1',
+ 'fo_fo': 'fo_FO.ISO8859-1',
+ 'fo_fo.iso88591': 'fo_FO.ISO8859-1',
+ 'fo_fo.iso885915': 'fo_FO.ISO8859-15',
+ 'fo_fo at euro': 'fo_FO.ISO8859-15',
+ 'fr': 'fr_FR.ISO8859-1',
+ 'fr_be': 'fr_BE.ISO8859-1',
+ 'fr_be.88591': 'fr_BE.ISO8859-1',
+ 'fr_be.iso88591': 'fr_BE.ISO8859-1',
+ 'fr_be.iso885915': 'fr_BE.ISO8859-15',
+ 'fr_be at euro': 'fr_BE.ISO8859-15',
+ 'fr_ca': 'fr_CA.ISO8859-1',
+ 'fr_ca.88591': 'fr_CA.ISO8859-1',
+ 'fr_ca.iso88591': 'fr_CA.ISO8859-1',
+ 'fr_ca.iso885915': 'fr_CA.ISO8859-15',
+ 'fr_ca at euro': 'fr_CA.ISO8859-15',
+ 'fr_ch': 'fr_CH.ISO8859-1',
+ 'fr_ch.88591': 'fr_CH.ISO8859-1',
+ 'fr_ch.iso88591': 'fr_CH.ISO8859-1',
+ 'fr_ch.iso885915': 'fr_CH.ISO8859-15',
+ 'fr_ch at euro': 'fr_CH.ISO8859-15',
+ 'fr_fr': 'fr_FR.ISO8859-1',
+ 'fr_fr.88591': 'fr_FR.ISO8859-1',
+ 'fr_fr.iso88591': 'fr_FR.ISO8859-1',
+ 'fr_fr.iso885915': 'fr_FR.ISO8859-15',
+ 'fr_fr at euro': 'fr_FR.ISO8859-15',
+ 'fr_lu': 'fr_LU.ISO8859-1',
+ 'fr_lu.88591': 'fr_LU.ISO8859-1',
+ 'fr_lu.iso88591': 'fr_LU.ISO8859-1',
+ 'fr_lu.iso885915': 'fr_LU.ISO8859-15',
+ 'fr_lu at euro': 'fr_LU.ISO8859-15',
+ 'fran\xe7ais': 'fr_FR.ISO8859-1',
+ 'fre_fr': 'fr_FR.ISO8859-1',
+ 'fre_fr.8859': 'fr_FR.ISO8859-1',
+ 'french': 'fr_FR.ISO8859-1',
+ 'french.iso88591': 'fr_CH.ISO8859-1',
+ 'french_france': 'fr_FR.ISO8859-1',
+ 'french_france.8859': 'fr_FR.ISO8859-1',
+ 'ga': 'ga_IE.ISO8859-1',
+ 'ga_ie': 'ga_IE.ISO8859-1',
+ 'ga_ie.iso88591': 'ga_IE.ISO8859-1',
+ 'ga_ie.iso885914': 'ga_IE.ISO8859-14',
+ 'ga_ie.iso885915': 'ga_IE.ISO8859-15',
+ 'ga_ie at euro': 'ga_IE.ISO8859-15',
+ 'galego': 'gl_ES.ISO8859-1',
+ 'galician': 'gl_ES.ISO8859-1',
+ 'gd': 'gd_GB.ISO8859-1',
+ 'gd_gb': 'gd_GB.ISO8859-1',
+ 'gd_gb.iso88591': 'gd_GB.ISO8859-1',
+ 'gd_gb.iso885914': 'gd_GB.ISO8859-14',
+ 'gd_gb.iso885915': 'gd_GB.ISO8859-15',
+ 'gd_gb at euro': 'gd_GB.ISO8859-15',
+ 'ger_de': 'de_DE.ISO8859-1',
+ 'ger_de.8859': 'de_DE.ISO8859-1',
+ 'german': 'de_DE.ISO8859-1',
+ 'german.iso88591': 'de_CH.ISO8859-1',
+ 'german_germany': 'de_DE.ISO8859-1',
+ 'german_germany.8859': 'de_DE.ISO8859-1',
+ 'gl': 'gl_ES.ISO8859-1',
+ 'gl_es': 'gl_ES.ISO8859-1',
+ 'gl_es.iso88591': 'gl_ES.ISO8859-1',
+ 'gl_es.iso885915': 'gl_ES.ISO8859-15',
+ 'gl_es at euro': 'gl_ES.ISO8859-15',
+ 'greek': 'el_GR.ISO8859-7',
+ 'greek.iso88597': 'el_GR.ISO8859-7',
+ 'gv': 'gv_GB.ISO8859-1',
+ 'gv_gb': 'gv_GB.ISO8859-1',
+ 'gv_gb.iso88591': 'gv_GB.ISO8859-1',
+ 'gv_gb.iso885914': 'gv_GB.ISO8859-14',
+ 'gv_gb.iso885915': 'gv_GB.ISO8859-15',
+ 'gv_gb at euro': 'gv_GB.ISO8859-15',
+ 'he': 'he_IL.ISO8859-8',
+ 'he_il': 'he_IL.ISO8859-8',
+ 'he_il.cp1255': 'he_IL.CP1255',
+ 'he_il.iso88598': 'he_IL.ISO8859-8',
+ 'he_il.microsoftcp1255': 'he_IL.CP1255',
+ 'hebrew': 'iw_IL.ISO8859-8',
+ 'hebrew.iso88598': 'iw_IL.ISO8859-8',
+ 'hi': 'hi_IN.ISCII-DEV',
+ 'hi_in': 'hi_IN.ISCII-DEV',
+ 'hi_in.isciidev': 'hi_IN.ISCII-DEV',
+ 'hr': 'hr_HR.ISO8859-2',
+ 'hr_hr': 'hr_HR.ISO8859-2',
+ 'hr_hr.iso88592': 'hr_HR.ISO8859-2',
+ 'hrvatski': 'hr_HR.ISO8859-2',
+ 'hu': 'hu_HU.ISO8859-2',
+ 'hu_hu': 'hu_HU.ISO8859-2',
+ 'hu_hu.iso88592': 'hu_HU.ISO8859-2',
+ 'hungarian': 'hu_HU.ISO8859-2',
+ 'icelandic': 'is_IS.ISO8859-1',
+ 'icelandic.iso88591': 'is_IS.ISO8859-1',
+ 'id': 'id_ID.ISO8859-1',
+ 'id_id': 'id_ID.ISO8859-1',
+ 'in': 'id_ID.ISO8859-1',
+ 'in_id': 'id_ID.ISO8859-1',
+ 'is': 'is_IS.ISO8859-1',
+ 'is_is': 'is_IS.ISO8859-1',
+ 'is_is.iso88591': 'is_IS.ISO8859-1',
+ 'is_is.iso885915': 'is_IS.ISO8859-15',
+ 'is_is at euro': 'is_IS.ISO8859-15',
+ 'iso-8859-1': 'en_US.ISO8859-1',
+ 'iso-8859-15': 'en_US.ISO8859-15',
+ 'iso8859-1': 'en_US.ISO8859-1',
+ 'iso8859-15': 'en_US.ISO8859-15',
+ 'iso_8859_1': 'en_US.ISO8859-1',
+ 'iso_8859_15': 'en_US.ISO8859-15',
+ 'it': 'it_IT.ISO8859-1',
+ 'it_ch': 'it_CH.ISO8859-1',
+ 'it_ch.iso88591': 'it_CH.ISO8859-1',
+ 'it_ch.iso885915': 'it_CH.ISO8859-15',
+ 'it_ch at euro': 'it_CH.ISO8859-15',
+ 'it_it': 'it_IT.ISO8859-1',
+ 'it_it.88591': 'it_IT.ISO8859-1',
+ 'it_it.iso88591': 'it_IT.ISO8859-1',
+ 'it_it.iso885915': 'it_IT.ISO8859-15',
+ 'it_it at euro': 'it_IT.ISO8859-15',
+ 'italian': 'it_IT.ISO8859-1',
+ 'italian.iso88591': 'it_IT.ISO8859-1',
+ 'iu': 'iu_CA.NUNACOM-8',
+ 'iu_ca': 'iu_CA.NUNACOM-8',
+ 'iu_ca.nunacom8': 'iu_CA.NUNACOM-8',
+ 'iw': 'he_IL.ISO8859-8',
+ 'iw_il': 'he_IL.ISO8859-8',
+ 'iw_il.iso88598': 'he_IL.ISO8859-8',
+ 'ja': 'ja_JP.eucJP',
+ 'ja.jis': 'ja_JP.JIS7',
+ 'ja.sjis': 'ja_JP.SJIS',
+ 'ja_jp': 'ja_JP.eucJP',
+ 'ja_jp.ajec': 'ja_JP.eucJP',
+ 'ja_jp.euc': 'ja_JP.eucJP',
+ 'ja_jp.eucjp': 'ja_JP.eucJP',
+ 'ja_jp.iso-2022-jp': 'ja_JP.JIS7',
+ 'ja_jp.iso2022jp': 'ja_JP.JIS7',
+ 'ja_jp.jis': 'ja_JP.JIS7',
+ 'ja_jp.jis7': 'ja_JP.JIS7',
+ 'ja_jp.mscode': 'ja_JP.SJIS',
+ 'ja_jp.sjis': 'ja_JP.SJIS',
+ 'ja_jp.ujis': 'ja_JP.eucJP',
+ 'japan': 'ja_JP.eucJP',
+ 'japanese': 'ja_JP.eucJP',
+ 'japanese-euc': 'ja_JP.eucJP',
+ 'japanese.euc': 'ja_JP.eucJP',
+ 'japanese.sjis': 'ja_JP.SJIS',
+ 'jp_jp': 'ja_JP.eucJP',
+ 'ka': 'ka_GE.GEORGIAN-ACADEMY',
+ 'ka_ge': 'ka_GE.GEORGIAN-ACADEMY',
+ 'ka_ge.georgianacademy': 'ka_GE.GEORGIAN-ACADEMY',
+ 'ka_ge.georgianps': 'ka_GE.GEORGIAN-PS',
+ 'ka_ge.georgianrs': 'ka_GE.GEORGIAN-ACADEMY',
+ 'kl': 'kl_GL.ISO8859-1',
+ 'kl_gl': 'kl_GL.ISO8859-1',
+ 'kl_gl.iso88591': 'kl_GL.ISO8859-1',
+ 'kl_gl.iso885915': 'kl_GL.ISO8859-15',
+ 'kl_gl at euro': 'kl_GL.ISO8859-15',
+ 'ko': 'ko_KR.eucKR',
+ 'ko_kr': 'ko_KR.eucKR',
+ 'ko_kr.euc': 'ko_KR.eucKR',
+ 'ko_kr.euckr': 'ko_KR.eucKR',
+ 'korean': 'ko_KR.eucKR',
+ 'korean.euc': 'ko_KR.eucKR',
+ 'kw': 'kw_GB.ISO8859-1',
+ 'kw_gb': 'kw_GB.ISO8859-1',
+ 'kw_gb.iso88591': 'kw_GB.ISO8859-1',
+ 'kw_gb.iso885914': 'kw_GB.ISO8859-14',
+ 'kw_gb.iso885915': 'kw_GB.ISO8859-15',
+ 'kw_gb at euro': 'kw_GB.ISO8859-15',
+ 'lithuanian': 'lt_LT.ISO8859-13',
+ 'lo': 'lo_LA.MULELAO-1',
+ 'lo_la': 'lo_LA.MULELAO-1',
+ 'lo_la.cp1133': 'lo_LA.IBM-CP1133',
+ 'lo_la.ibmcp1133': 'lo_LA.IBM-CP1133',
+ 'lo_la.mulelao1': 'lo_LA.MULELAO-1',
+ 'lt': 'lt_LT.ISO8859-13',
+ 'lt_lt': 'lt_LT.ISO8859-13',
+ 'lt_lt.iso885913': 'lt_LT.ISO8859-13',
+ 'lt_lt.iso88594': 'lt_LT.ISO8859-4',
+ 'lv': 'lv_LV.ISO8859-13',
+ 'lv_lv': 'lv_LV.ISO8859-13',
+ 'lv_lv.iso885913': 'lv_LV.ISO8859-13',
+ 'lv_lv.iso88594': 'lv_LV.ISO8859-4',
+ 'mi': 'mi_NZ.ISO8859-1',
+ 'mi_nz': 'mi_NZ.ISO8859-1',
+ 'mi_nz.iso88591': 'mi_NZ.ISO8859-1',
+ 'mk': 'mk_MK.ISO8859-5',
+ 'mk_mk': 'mk_MK.ISO8859-5',
+ 'mk_mk.cp1251': 'mk_MK.CP1251',
+ 'mk_mk.iso88595': 'mk_MK.ISO8859-5',
+ 'mk_mk.microsoftcp1251': 'mk_MK.CP1251',
+ 'ms': 'ms_MY.ISO8859-1',
+ 'ms_my': 'ms_MY.ISO8859-1',
+ 'ms_my.iso88591': 'ms_MY.ISO8859-1',
+ 'mt': 'mt_MT.ISO8859-3',
+ 'mt_mt': 'mt_MT.ISO8859-3',
+ 'mt_mt.iso88593': 'mt_MT.ISO8859-3',
+ 'nb': 'nb_NO.ISO8859-1',
+ 'nb_no': 'nb_NO.ISO8859-1',
+ 'nb_no.88591': 'nb_NO.ISO8859-1',
+ 'nb_no.iso88591': 'nb_NO.ISO8859-1',
+ 'nb_no.iso885915': 'nb_NO.ISO8859-15',
+ 'nb_no at euro': 'nb_NO.ISO8859-15',
+ 'nl': 'nl_NL.ISO8859-1',
+ 'nl_be': 'nl_BE.ISO8859-1',
+ 'nl_be.88591': 'nl_BE.ISO8859-1',
+ 'nl_be.iso88591': 'nl_BE.ISO8859-1',
+ 'nl_be.iso885915': 'nl_BE.ISO8859-15',
+ 'nl_be at euro': 'nl_BE.ISO8859-15',
+ 'nl_nl': 'nl_NL.ISO8859-1',
+ 'nl_nl.88591': 'nl_NL.ISO8859-1',
+ 'nl_nl.iso88591': 'nl_NL.ISO8859-1',
+ 'nl_nl.iso885915': 'nl_NL.ISO8859-15',
+ 'nl_nl at euro': 'nl_NL.ISO8859-15',
+ 'nn': 'nn_NO.ISO8859-1',
+ 'nn_no': 'nn_NO.ISO8859-1',
+ 'nn_no.88591': 'nn_NO.ISO8859-1',
+ 'nn_no.iso88591': 'nn_NO.ISO8859-1',
+ 'nn_no.iso885915': 'nn_NO.ISO8859-15',
+ 'nn_no at euro': 'nn_NO.ISO8859-15',
+ 'no': 'no_NO.ISO8859-1',
+ 'no at nynorsk': 'ny_NO.ISO8859-1',
+ 'no_no': 'no_NO.ISO8859-1',
+ 'no_no.88591': 'no_NO.ISO8859-1',
+ 'no_no.iso88591': 'no_NO.ISO8859-1',
+ 'no_no.iso885915': 'no_NO.ISO8859-15',
+ 'no_no at euro': 'no_NO.ISO8859-15',
+ 'norwegian': 'no_NO.ISO8859-1',
+ 'norwegian.iso88591': 'no_NO.ISO8859-1',
+ 'ny': 'ny_NO.ISO8859-1',
+ 'ny_no': 'ny_NO.ISO8859-1',
+ 'ny_no.88591': 'ny_NO.ISO8859-1',
+ 'ny_no.iso88591': 'ny_NO.ISO8859-1',
+ 'ny_no.iso885915': 'ny_NO.ISO8859-15',
+ 'ny_no at euro': 'ny_NO.ISO8859-15',
+ 'nynorsk': 'nn_NO.ISO8859-1',
+ 'oc': 'oc_FR.ISO8859-1',
+ 'oc_fr': 'oc_FR.ISO8859-1',
+ 'oc_fr.iso88591': 'oc_FR.ISO8859-1',
+ 'oc_fr.iso885915': 'oc_FR.ISO8859-15',
+ 'oc_fr at euro': 'oc_FR.ISO8859-15',
+ 'pd': 'pd_US.ISO8859-1',
+ 'pd_de': 'pd_DE.ISO8859-1',
+ 'pd_de.iso88591': 'pd_DE.ISO8859-1',
+ 'pd_de.iso885915': 'pd_DE.ISO8859-15',
+ 'pd_de at euro': 'pd_DE.ISO8859-15',
+ 'pd_us': 'pd_US.ISO8859-1',
+ 'pd_us.iso88591': 'pd_US.ISO8859-1',
+ 'pd_us.iso885915': 'pd_US.ISO8859-15',
+ 'pd_us at euro': 'pd_US.ISO8859-15',
+ 'ph': 'ph_PH.ISO8859-1',
+ 'ph_ph': 'ph_PH.ISO8859-1',
+ 'ph_ph.iso88591': 'ph_PH.ISO8859-1',
+ 'pl': 'pl_PL.ISO8859-2',
+ 'pl_pl': 'pl_PL.ISO8859-2',
+ 'pl_pl.iso88592': 'pl_PL.ISO8859-2',
+ 'polish': 'pl_PL.ISO8859-2',
+ 'portuguese': 'pt_PT.ISO8859-1',
+ 'portuguese.iso88591': 'pt_PT.ISO8859-1',
+ 'portuguese_brazil': 'pt_BR.ISO8859-1',
+ 'portuguese_brazil.8859': 'pt_BR.ISO8859-1',
+ 'posix': 'C',
+ 'posix-utf2': 'C',
+ 'pp': 'pp_AN.ISO8859-1',
+ 'pp_an': 'pp_AN.ISO8859-1',
+ 'pp_an.iso88591': 'pp_AN.ISO8859-1',
+ 'pt': 'pt_PT.ISO8859-1',
+ 'pt_br': 'pt_BR.ISO8859-1',
+ 'pt_br.88591': 'pt_BR.ISO8859-1',
+ 'pt_br.iso88591': 'pt_BR.ISO8859-1',
+ 'pt_br.iso885915': 'pt_BR.ISO8859-15',
+ 'pt_br at euro': 'pt_BR.ISO8859-15',
+ 'pt_pt': 'pt_PT.ISO8859-1',
+ 'pt_pt.88591': 'pt_PT.ISO8859-1',
+ 'pt_pt.iso88591': 'pt_PT.ISO8859-1',
+ 'pt_pt.iso885915': 'pt_PT.ISO8859-15',
+ 'pt_pt.utf8 at euro': 'pt_PT.UTF-8',
+ 'pt_pt at euro': 'pt_PT.ISO8859-15',
+ 'ro': 'ro_RO.ISO8859-2',
+ 'ro_ro': 'ro_RO.ISO8859-2',
+ 'ro_ro.iso88592': 'ro_RO.ISO8859-2',
+ 'romanian': 'ro_RO.ISO8859-2',
+ 'ru': 'ru_RU.ISO8859-5',
+ 'ru_ru': 'ru_RU.ISO8859-5',
+ 'ru_ru.cp1251': 'ru_RU.CP1251',
+ 'ru_ru.iso88595': 'ru_RU.ISO8859-5',
+ 'ru_ru.koi8r': 'ru_RU.KOI8-R',
+ 'ru_ru.microsoftcp1251': 'ru_RU.CP1251',
+ 'ru_ua': 'ru_UA.KOI8-U',
+ 'ru_ua.cp1251': 'ru_UA.CP1251',
+ 'ru_ua.koi8u': 'ru_UA.KOI8-U',
+ 'ru_ua.microsoftcp1251': 'ru_UA.CP1251',
+ 'rumanian': 'ro_RO.ISO8859-2',
+ 'russian': 'ru_RU.ISO8859-5',
+ 'se_no': 'se_NO.UTF-8',
+ 'serbocroatian': 'sh_YU.ISO8859-2',
+ 'sh': 'sh_YU.ISO8859-2',
+ 'sh_hr': 'sh_HR.ISO8859-2',
+ 'sh_hr.iso88592': 'sh_HR.ISO8859-2',
+ 'sh_sp': 'sh_YU.ISO8859-2',
+ 'sh_yu': 'sh_YU.ISO8859-2',
+ 'sk': 'sk_SK.ISO8859-2',
+ 'sk_sk': 'sk_SK.ISO8859-2',
+ 'sk_sk.iso88592': 'sk_SK.ISO8859-2',
+ 'sl': 'sl_SI.ISO8859-2',
+ 'sl_cs': 'sl_CS.ISO8859-2',
+ 'sl_si': 'sl_SI.ISO8859-2',
+ 'sl_si.iso88592': 'sl_SI.ISO8859-2',
+ 'slovak': 'sk_SK.ISO8859-2',
+ 'slovene': 'sl_SI.ISO8859-2',
+ 'slovenian': 'sl_SI.ISO8859-2',
+ 'sp': 'sp_YU.ISO8859-5',
+ 'sp_yu': 'sp_YU.ISO8859-5',
+ 'spanish': 'es_ES.ISO8859-1',
+ 'spanish.iso88591': 'es_ES.ISO8859-1',
+ 'spanish_spain': 'es_ES.ISO8859-1',
+ 'spanish_spain.8859': 'es_ES.ISO8859-1',
+ 'sq': 'sq_AL.ISO8859-2',
+ 'sq_al': 'sq_AL.ISO8859-2',
+ 'sq_al.iso88592': 'sq_AL.ISO8859-2',
+ 'sr': 'sr_YU.ISO8859-5',
+ 'sr at cyrillic': 'sr_YU.ISO8859-5',
+ 'sr_sp': 'sr_SP.ISO8859-2',
+ 'sr_yu': 'sr_YU.ISO8859-5',
+ 'sr_yu.cp1251 at cyrillic': 'sr_YU.CP1251',
+ 'sr_yu.iso88592': 'sr_YU.ISO8859-2',
+ 'sr_yu.iso88595': 'sr_YU.ISO8859-5',
+ 'sr_yu.iso88595 at cyrillic': 'sr_YU.ISO8859-5',
+ 'sr_yu.microsoftcp1251 at cyrillic': 'sr_YU.CP1251',
+ 'sr_yu.utf8 at cyrillic': 'sr_YU.UTF-8',
+ 'sr_yu at cyrillic': 'sr_YU.ISO8859-5',
+ 'sv': 'sv_SE.ISO8859-1',
+ 'sv_fi': 'sv_FI.ISO8859-1',
+ 'sv_fi.iso88591': 'sv_FI.ISO8859-1',
+ 'sv_fi.iso885915': 'sv_FI.ISO8859-15',
+ 'sv_fi at euro': 'sv_FI.ISO8859-15',
+ 'sv_se': 'sv_SE.ISO8859-1',
+ 'sv_se.88591': 'sv_SE.ISO8859-1',
+ 'sv_se.iso88591': 'sv_SE.ISO8859-1',
+ 'sv_se.iso885915': 'sv_SE.ISO8859-15',
+ 'sv_se at euro': 'sv_SE.ISO8859-15',
+ 'swedish': 'sv_SE.ISO8859-1',
+ 'swedish.iso88591': 'sv_SE.ISO8859-1',
+ 'ta': 'ta_IN.TSCII-0',
+ 'ta_in': 'ta_IN.TSCII-0',
+ 'ta_in.tscii': 'ta_IN.TSCII-0',
+ 'ta_in.tscii0': 'ta_IN.TSCII-0',
+ 'tg': 'tg_TJ.KOI8-C',
+ 'tg_tj': 'tg_TJ.KOI8-C',
+ 'tg_tj.koi8c': 'tg_TJ.KOI8-C',
+ 'th': 'th_TH.ISO8859-11',
+ 'th_th': 'th_TH.ISO8859-11',
+ 'th_th.iso885911': 'th_TH.ISO8859-11',
+ 'th_th.tactis': 'th_TH.TIS620',
+ 'th_th.tis620': 'th_TH.TIS620',
+ 'thai': 'th_TH.ISO8859-11',
+ 'tl': 'tl_PH.ISO8859-1',
+ 'tl_ph': 'tl_PH.ISO8859-1',
+ 'tl_ph.iso88591': 'tl_PH.ISO8859-1',
+ 'tr': 'tr_TR.ISO8859-9',
+ 'tr_tr': 'tr_TR.ISO8859-9',
+ 'tr_tr.iso88599': 'tr_TR.ISO8859-9',
+ 'tt': 'tt_RU.TATAR-CYR',
+ 'tt_ru': 'tt_RU.TATAR-CYR',
+ 'tt_ru.koi8c': 'tt_RU.KOI8-C',
+ 'tt_ru.tatarcyr': 'tt_RU.TATAR-CYR',
+ 'turkish': 'tr_TR.ISO8859-9',
+ 'turkish.iso88599': 'tr_TR.ISO8859-9',
+ 'uk': 'uk_UA.KOI8-U',
+ 'uk_ua': 'uk_UA.KOI8-U',
+ 'uk_ua.cp1251': 'uk_UA.CP1251',
+ 'uk_ua.iso88595': 'uk_UA.ISO8859-5',
+ 'uk_ua.koi8u': 'uk_UA.KOI8-U',
+ 'uk_ua.microsoftcp1251': 'uk_UA.CP1251',
+ 'univ': 'en_US.utf',
+ 'universal': 'en_US.utf',
+ 'universal.utf8 at ucs4': 'en_US.UTF-8',
+ 'ur': 'ur_PK.CP1256',
+ 'ur_pk': 'ur_PK.CP1256',
+ 'ur_pk.cp1256': 'ur_PK.CP1256',
+ 'ur_pk.microsoftcp1256': 'ur_PK.CP1256',
+ 'uz': 'uz_UZ.UTF-8',
+ 'uz_uz': 'uz_UZ.UTF-8',
+ 'vi': 'vi_VN.TCVN',
+ 'vi_vn': 'vi_VN.TCVN',
+ 'vi_vn.tcvn': 'vi_VN.TCVN',
+ 'vi_vn.tcvn5712': 'vi_VN.TCVN',
+ 'vi_vn.viscii': 'vi_VN.VISCII',
+ 'vi_vn.viscii111': 'vi_VN.VISCII',
+ 'wa': 'wa_BE.ISO8859-1',
+ 'wa_be': 'wa_BE.ISO8859-1',
+ 'wa_be.iso88591': 'wa_BE.ISO8859-1',
+ 'wa_be.iso885915': 'wa_BE.ISO8859-15',
+ 'wa_be at euro': 'wa_BE.ISO8859-15',
+ 'yi': 'yi_US.CP1255',
+ 'yi_us': 'yi_US.CP1255',
+ 'yi_us.cp1255': 'yi_US.CP1255',
+ 'yi_us.microsoftcp1255': 'yi_US.CP1255',
+ 'zh': 'zh_CN.eucCN',
+ 'zh_cn': 'zh_CN.gb2312',
+ 'zh_cn.big5': 'zh_TW.big5',
+ 'zh_cn.euc': 'zh_CN.eucCN',
+ 'zh_cn.gb18030': 'zh_CN.gb18030',
+ 'zh_cn.gb2312': 'zh_CN.gb2312',
+ 'zh_cn.gbk': 'zh_CN.gbk',
+ 'zh_hk': 'zh_HK.big5hkscs',
+ 'zh_hk.big5': 'zh_HK.big5',
+ 'zh_hk.big5hkscs': 'zh_HK.big5hkscs',
+ 'zh_tw': 'zh_TW.big5',
+ 'zh_tw.big5': 'zh_TW.big5',
+ 'zh_tw.euc': 'zh_TW.eucTW',
+}
+
+
+def _normalize(space, localename):
+ """ Returns a normalized locale code for the given locale
+ name.
+
+ The returned locale code is formatted for use with
+ setlocale().
+
+ If normalization fails, the original name is returned
+ unchanged.
+
+ If the given encoding is not known, the function defaults to
+ the default encoding for the locale code just like setlocale()
+ does.
+
+ """
+ # Normalize the locale name and extract the encoding
+ fullname = localename.lower()
+ if ':' in fullname:
+ # ':' is sometimes used as encoding delimiter.
+ fullname = fullname.replace(':', '.')
+ if '.' in fullname:
+ langname, encoding = fullname.split('.')[:2]
+ fullname = langname + '.' + encoding
+ else:
+ langname = fullname
+ encoding = ''
+
+ # First lookup: fullname (possibly with encoding)
+ norm_encoding = encoding.replace('-', '')
+ norm_encoding = norm_encoding.replace('_', '')
+ lookup_name = langname + '.' + encoding
+ code = locale_alias.get(lookup_name, None)
+ if code is not None:
+ return space.wrap(code)
+ #print 'first lookup failed'
+
+ # Second try: langname (without encoding)
+ code = locale_alias.get(langname, None)
+ if code is not None:
+ #print 'langname lookup succeeded'
+ if '.' in code:
+ langname, defenc = code.split('.')
+ else:
+ langname = code
+ defenc = ''
+ if encoding:
+ # Convert the encoding to a C lib compatible encoding string
+ norm_encoding = encodings.normalize_encoding(encoding)
+ #print 'norm encoding: %r' % norm_encoding
+ norm_encoding = encodings.aliases.aliases.get(norm_encoding,
+ norm_encoding)
+ #print 'aliased encoding: %r' % norm_encoding
+ encoding = locale_encoding_alias.get(norm_encoding,
+ norm_encoding)
+ else:
+ encoding = defenc
+ #print 'found encoding %r' % encoding
+ if encoding:
+ return space.wrap(langname + '.' + encoding)
+ else:
+ return space.wrap(langname)
+
+ else:
+ return space.wrap(localename)
+
+def _parse_localename(space, localename):
+ """ Parses the locale code for localename and returns the
+ result as tuple (language code, encoding).
+
+ The localename is normalized and passed through the locale
+ alias engine. A ValueError is raised in case the locale name
+ cannot be parsed.
+
+ The language code corresponds to RFC 1766. code and encoding
+ can be None in case the values cannot be determined or are
+ unknown to this implementation.
+
+ """
+ code = space.str_w(_normalize(space, localename))
+ if '@' in code:
+ # deal with locale modifiers
+ code, modifier = code.split('@')
+ if modifier == 'euro' and '.' not in code:
+ # Assume Latin-9 for @euro locales. This is bogus,
+ # since some systems may use other encodings for these
+ # locales. Also, we ignore other modifiers.
+ return space.wrap([code, 'iso-8859-15'])
+
+ if '.' in code:
+ a, b = code.split('.')[:2]
+ return space.wrap([a, b])
+ elif code == 'C':
+ return space.wrap([None, None])
+ raise OperationError(space.w_ValueError,
+ space.wrap('unknown locale: %s' % localename))
+
+def _getlocale(space, category):
+ localename = space.str_w(_setlocale(space, category))
+ if category == LC_ALL and ';' in localename:
+ raise OperationError(space.w_TypeError,
+ space.wrap('category LC_ALL is not supported'))
+ return _parse_localename(space, localename)
+
+def _getlang(space):
+ # figure out what the current language is set to.
+ # XXX: reimplemented in ctypes locale._setlocale()
+ return _getlocale(space, LC_TIME)
+
+def _struct_time(space, tuple):
+ w_struct_time = _get_module_object(space, 'struct_time')
+ w_time_tuple = space.newtuple(tuple)
+ return space.call_function(w_struct_time, w_time_tuple)
+
+class LocaleTime(object):
+ """Stores and handles locale-specific information related to time.
+
+ ATTRIBUTES:
+ f_weekday -- full weekday names (7-item list)
+ a_weekday -- abbreviated weekday names (7-item list)
+ f_month -- full month names (13-item list; dummy value in [0], which
+ is added by code)
+ a_month -- abbreviated month names (13-item list, dummy value in
+ [0], which is added by code)
+ am_pm -- AM/PM representation (2-item list)
+ LC_date_time -- format string for date/time representation (string)
+ LC_date -- format string for date representation (string)
+ LC_time -- format string for time representation (string)
+ timezone -- daylight- and non-daylight-savings timezone representation
+ (2-item list of sets)
+ lang -- Language used by instance (2-item tuple)
+ """
+
+ def __init__(self, space):
+ """Set all attributes.
+
+ Order of methods called matters for dependency reasons.
+
+ The locale language is set at the offset and then checked again before
+ exiting. This is to make sure that the attributes were not set with a
+ mix of information from more than one locale. This would most likely
+ happen when using threads where one thread calls a locale-dependent
+ function while another thread changes the locale while the function in
+ the other thread is still running. Proper coding would call for
+ locks to prevent changing the locale while locale-dependent code is
+ running. The check here is done in case someone does not think about
+ doing this.
+
+ Only other possible issue is if someone changed the timezone and did
+ not call tz.tzset . That is an issue for the programmer, though,
+ since changing the timezone is worthless without that call.
+
+ """
+ self.space = space
+ self.lang = self.space.unpackiterable(_getlang(self.space))
+ self.__calc_weekday()
+ self.__calc_month()
+ self.__calc_am_pm()
+ self.__calc_timezone()
+ self.__calc_date_time()
+ print self.lang, _getlang(self.space)
+ if self.space.unpackiterable(_getlang(self.space)) != self.lang:
+ raise ValueError("locale changed during initialization")
+
+ def __pad(self, seq, front):
+ # Add '' to seq to either the front (is True), else the back.
+ seq = list(seq)
+ if front:
+ seq.insert(0, '')
+ else:
+ seq.append('')
+ return seq
+
+ def __calc_weekday(self):
+ # Set self.a_weekday and self.f_weekday using the calendar
+ # module.
+ a_weekday = [calendar.day_abbr[i].lower() for i in range(7)]
+ f_weekday = [calendar.day_name[i].lower() for i in range(7)]
+ self.a_weekday = a_weekday
+ self.f_weekday = f_weekday
+
+ def __calc_month(self):
+ # Set self.f_month and self.a_month using the calendar module.
+ a_month = [calendar.month_abbr[i].lower() for i in range(13)]
+ f_month = [calendar.month_name[i].lower() for i in range(13)]
+ self.a_month = a_month
+ self.f_month = f_month
+
+ def __calc_am_pm(self):
+ # Set self.am_pm by using strftime().
+
+ # The magic date (1999,3,17,hour,44,55,2,76,0) is not really that
+ # magical; just happened to have used it everywhere else where a
+ # static date was needed.
+ am_pm = []
+ for hour in (01,22):
+ time_tuple = [1999, 3, 17, hour, 44, 55, 2, 76, 0]
+ w_res = strftime(self.space, self.space.wrap("%p"),
+ self.space.wrap(time_tuple))
+ res = self.space.str_w(w_res)
+ am_pm.append(res.lower())
+ self.am_pm = am_pm
+
+ def __calc_date_time(self):
+ # Set self.date_time, self.date, & self.time by using strftime().
+
+ # Use (1999,3,17,22,44,55,2,76,0) for magic date because the amount of
+ # overloaded numbers is minimized. The order in which searches for
+ # values within the format string is very important; it eliminates
+ # possible ambiguity for what something represents.
+ time_tuple = [1999, 3, 17, 22, 44, 55, 2, 76, 0]
+ date_time = [None, None, None]
+ date_time[0] = self.space.str_w(strftime(self.space,
+ self.space.wrap("%c"), self.space.wrap(time_tuple))).lower()
+ date_time[1] = self.space.str_w(strftime(self.space,
+ self.space.wrap("%x"), self.space.wrap(time_tuple))).lower()
+ date_time[2] = self.space.str_w(strftime(self.space,
+ self.space.wrap("%X"), self.space.wrap(time_tuple))).lower()
+ replacement_pairs = [('%', '%%'), (self.f_weekday[2], '%A'),
+ (self.f_month[3], '%B'), (self.a_weekday[2], '%a'),
+ (self.a_month[3], '%b'), (self.am_pm[1], '%p'),
+ ('1999', '%Y'), ('99', '%y'), ('22', '%H'),
+ ('44', '%M'), ('55', '%S'), ('76', '%j'),
+ ('17', '%d'), ('03', '%m'), ('3', '%m'),
+ # '3' needed for when no leading zero.
+ ('2', '%w'), ('10', '%I')]
+ replacement_pairs.extend([(tz, "%Z") for tz_values in self.timezone
+ for tz in tz_values])
+ for offset,directive in ((0,'%c'), (1,'%x'), (2,'%X')):
+ current_format = date_time[offset]
+ for old, new in replacement_pairs:
+ # Must deal with possible lack of locale info
+ # manifesting itself as the empty string (e.g., Swedish's
+ # lack of AM/PM info) or a platform returning a tuple of empty
+ # strings (e.g., MacOS 9 having timezone as ('','')).
+ if old:
+ current_format = current_format.replace(old, new)
+ # If %W is used, then Sunday, 2005-01-03 will fall on week 0 since
+ # 2005-01-03 occurs before the first Monday of the year. Otherwise
+ # %U is used.
+ time_tuple = [1999, 1, 3, 1, 1, 1, 6, 3, 0]
+ res = self.space.str_w(strftime(self.space,
+ self.space.wrap(directive), self.space.wrap(time_tuple)))
+ if '00' in res:
+ U_W = '%W'
+ else:
+ U_W = '%U'
+ date_time[offset] = current_format.replace('11', U_W)
+ self.LC_date_time = date_time[0]
+ self.LC_date = date_time[1]
+ self.LC_time = date_time[2]
+
+ def __calc_timezone(self):
+ # Set self.timezone by using tzname.
+ # Do not worry about possibility of tzname[0] == timetzname[1]
+ # and daylight; handle that in strptime .
+
+ # get tzname
+ w_tzname = _get_module_object(self.space, "tzname")
+ tzname_w = self.space.unpackiterable(w_tzname)
+ tzname = [self.space.str_w(i) for i in tzname_w]
+ # get daylight
+ w_daylight = _get_module_object(self.space, "daylight")
+ daylight = self.space.int_w(w_daylight)
+
+ try:
+ tzset(self.space)
+ except AttributeError:
+ pass
+ no_saving = frozenset(["utc", "gmt", tzname[0].lower()])
+ if daylight:
+ has_saving = frozenset([tzname[1].lower()])
+ else:
+ has_saving = frozenset()
+ self.timezone = (no_saving, has_saving)
+
+class TimeRE(object):
+ """Handle conversion from format directives to regexes."""
+
+ def __init__(self, space, locale_time=None):
+ """Create keys/values.
+
+ Order of execution is important for dependency reasons.
+
+ """
+ self._dict = {}
+ self.space = space
+ if locale_time:
+ self.locale_time = locale_time
+ else:
+ self.locale_time = LocaleTime(self.space)
+ self._dict.update({
+ # The " \d" part of the regex is to make %c from ANSI C work
+ 'd': r"(?P<d>3[0-1]|[1-2]\d|0[1-9]|[1-9]| [1-9])",
+ 'H': r"(?P<H>2[0-3]|[0-1]\d|\d)",
+ 'I': r"(?P<I>1[0-2]|0[1-9]|[1-9])",
+ 'j': r"(?P<j>36[0-6]|3[0-5]\d|[1-2]\d\d|0[1-9]\d|00[1-9]|[1-9]\d|0[1-9]|[1-9])",
+ 'm': r"(?P<m>1[0-2]|0[1-9]|[1-9])",
+ 'M': r"(?P<M>[0-5]\d|\d)",
+ 'S': r"(?P<S>6[0-1]|[0-5]\d|\d)",
+ 'U': r"(?P<U>5[0-3]|[0-4]\d|\d)",
+ 'w': r"(?P<w>[0-6])",
+ # W is set below by using 'U'
+ 'y': r"(?P<y>\d\d)",
+ #XXX: Does 'Y' need to worry about having less or more than
+ # 4 digits?
+ 'Y': r"(?P<Y>\d\d\d\d)",
+ 'A': self.__seqToRE(self.locale_time.f_weekday, 'A'),
+ 'a': self.__seqToRE(self.locale_time.a_weekday, 'a'),
+ 'B': self.__seqToRE(self.locale_time.f_month[1:], 'B'),
+ 'b': self.__seqToRE(self.locale_time.a_month[1:], 'b'),
+ 'p': self.__seqToRE(self.locale_time.am_pm, 'p'),
+ 'Z': self.__seqToRE((tz for tz_names in self.locale_time.timezone
+ for tz in tz_names),
+ 'Z'),
+ '%': '%'})
+ self._dict['W'] = self._dict['U'].replace('U', 'W')
+ self._dict['c'] = self.pattern(self.locale_time.LC_date_time)
+ self._dict['x'] = self.pattern(self.locale_time.LC_date)
+ self._dict['X'] = self.pattern(self.locale_time.LC_time)
+
+ def __seqToRE(self, to_convert, directive):
+ """Convert a list to a regex string for matching a directive.
+
+ Want possible matching values to be from longest to shortest. This
+ prevents the possibility of a match occuring for a value that also
+ a substring of a larger value that should have matched (e.g., 'abc'
+ matching when 'abcdef' should have been the match).
+
+ """
+ to_convert = sorted(to_convert, key=len, reverse=True)
+ for value in to_convert:
+ if value != '':
+ break
+ else:
+ return ''
+ regex = '|'.join(re_escape(stuff) for stuff in to_convert)
+ regex = '(?P<%s>%s' % (directive, regex)
+ return '%s)' % regex
+
+ def pattern(self, format):
+ """Return regex pattern for the format string.
+
+ Need to make sure that any characters that might be interpreted as
+ regex syntax are escaped.
+
+ """
+ processed_format = ''
+ # The sub() call escapes all characters that might be misconstrued
+ # as regex syntax. Cannot use re.escape since we have to deal with
+ # format directives (%m, etc.).
+ regex_chars = re_compile(r"([\\.^$*+?\(\){}\[\]|])")
+ format = regex_chars.sub(r"\\\1", format)
+ whitespace_replacement = re_compile('\s+')
+ format = whitespace_replacement.sub('\s*', format)
+ while '%' in format:
+ directive_index = format.index('%')+1
+ processed_format = "%s%s%s" % (processed_format,
+ format[:directive_index-1],
+ self._dict[format[directive_index]])
+ format = format[directive_index+1:]
+ return "%s%s" % (processed_format, format)
+
+ def compile(self, format):
+ """Return a compiled re object for the format string."""
+ return re_compile(self.pattern(format), IGNORECASE)
+
+def _strptime(space, data_string, format="%a %b %d %H:%M:%S %Y"):
+ """Return a time struct based on the input string and the format string."""
+
+ _TimeRE_cache = TimeRE(space)
+ _CACHE_MAX_SIZE = 5 # Max number of regexes stored in _regex_cache
+ _regex_cache = {}
+
+ # get tzname
+ w_tzname = _get_module_object(space, "tzname")
+ tzname_w = space.unpackiterable(w_tzname)
+ tzname = [space.str_w(i) for i in tzname_w]
+ # get daylight
+ w_daylight = _get_module_object(space, "daylight")
+ daylight = space.int_w(w_daylight)
+
+ time_re = _TimeRE_cache
+ locale_time = time_re.locale_time
+ if _getlang(space) != locale_time.lang:
+ _TimeRE_cache = TimeRE(space)
+ _regex_cache = {}
+ if len(_regex_cache) > _CACHE_MAX_SIZE:
+ _regex_cache.clear()
+ format_regex = _regex_cache.get(format)
+ if not format_regex:
+ try:
+ format_regex = time_re.compile(format)
+ # KeyError raised when a bad format is found; can be specified as
+ # \\, in which case it was a stray % but with a space after it
+ except KeyError, err:
+ bad_directive = err.args[0]
+ if bad_directive == "\\":
+ bad_directive = "%"
+ del err
+ msg = "'%s' is a bad directive in format '%s'" %\
+ (bad_directive, format)
+ raise OperationError(space.w_ValueError,
+ space.wrap(msg))
+ # IndexError only occurs when the format string is "%"
+ except IndexError:
+ raise OperationError(space.w_ValueError,
+ space.wrap("stray %% in format '%s'" % format))
+ _regex_cache[format] = format_regex
+
+ found = format_regex.match(data_string)
+ if not found:
+ raise OperationError(space.w_ValueError,
+ space.wrap("time data did not match format: data=%s fmt=%s" % \
+ (data_string, format)))
+ if len(data_string) != found.end():
+ raise OperationError(space.w_ValueError,
+ space.wrap("unconverted data remains: %s" % \
+ data_string[found.end():]))
+ year = 1900
+ month = day = 1
+ hour = minute = second = 0
+ tz = -1
+ # Default to -1 to signify that values not known; not critical to have,
+ # though
+ week_of_year = -1
+ week_of_year_start = -1
+ # weekday and julian defaulted to -1 so as to signal need to calculate
+ # values
+ weekday = julian = -1
+ found_dict = found.groupdict()
+ for group_key in found_dict.iterkeys():
+ # Directives not explicitly handled below:
+ # c, x, X
+ # handled by making out of other directives
+ # U, W
+ # worthless without day of the week
+ if group_key == 'y':
+ year = int(found_dict['y'])
+ # Open Group specification for strptime() states that a %y
+ #value in the range of [00, 68] is in the century 2000, while
+ #[69,99] is in the century 1900
+ if year <= 68:
+ year += 2000
+ else:
+ year += 1900
+ elif group_key == 'Y':
+ year = int(found_dict['Y'])
+ elif group_key == 'm':
+ month = int(found_dict['m'])
+ elif group_key == 'B':
+ month = locale_time.f_month.index(found_dict['B'].lower())
+ elif group_key == 'b':
+ month = locale_time.a_month.index(found_dict['b'].lower())
+ elif group_key == 'd':
+ day = int(found_dict['d'])
+ elif group_key == 'H':
+ hour = int(found_dict['H'])
+ elif group_key == 'I':
+ hour = int(found_dict['I'])
+ ampm = found_dict.get('p', '').lower()
+ # If there was no AM/PM indicator, we'll treat this like AM
+ if ampm in ('', locale_time.am_pm[0]):
+ # We're in AM so the hour is correct unless we're
+ # looking at 12 midnight.
+ # 12 midnight == 12 AM == hour 0
+ if hour == 12:
+ hour = 0
+ elif ampm == locale_time.am_pm[1]:
+ # We're in PM so we need to add 12 to the hour unless
+ # we're looking at 12 noon.
+ # 12 noon == 12 PM == hour 12
+ if hour != 12:
+ hour += 12
+ elif group_key == 'M':
+ minute = int(found_dict['M'])
+ elif group_key == 'S':
+ second = int(found_dict['S'])
+ elif group_key == 'A':
+ weekday = locale_time.f_weekday.index(found_dict['A'].lower())
+ elif group_key == 'a':
+ weekday = locale_time.a_weekday.index(found_dict['a'].lower())
+ elif group_key == 'w':
+ weekday = int(found_dict['w'])
+ if weekday == 0:
+ weekday = 6
+ else:
+ weekday -= 1
+ elif group_key == 'j':
+ julian = int(found_dict['j'])
+ elif group_key in ('U', 'W'):
+ week_of_year = int(found_dict[group_key])
+ if group_key == 'U':
+ # U starts week on Sunday
+ week_of_year_start = 6
+ else:
+ # W starts week on Monday
+ week_of_year_start = 0
+ elif group_key == 'Z':
+ # Since -1 is default value only need to worry about setting tz if
+ # it can be something other than -1.
+ found_zone = found_dict['Z'].lower()
+ for value, tz_values in enumerate(locale_time.timezone):
+ if found_zone in tz_values:
+ # Deal with bad locale setup where timezone names are the
+ # same and yet daylight is true; too ambiguous to
+ # be able to tell what timezone has daylight savings
+ if (tzname[0] == tzname[1] and
+ daylight and found_zone not in ("utc", "gmt")):
+ break
+ else:
+ tz = value
+ break
+ # If we know the week of the year and what day of that week, we can figure
+ # out the Julian day of the year
+ # Calculations below assume 0 is a Monday
+ if julian == -1 and week_of_year != -1 and weekday != -1:
+ # Calculate how many days in week 0
+ first_weekday = datetime_date(year, 1, 1).weekday()
+ preceeding_days = 7 - first_weekday
+ if preceeding_days == 7:
+ preceeding_days = 0
+ # Adjust for U directive so that calculations are not dependent on
+ # directive used to figure out week of year
+ if weekday == 6 and week_of_year_start == 6:
+ week_of_year -= 1
+ # If a year starts and ends on a Monday but a week is specified to
+ # start on a Sunday we need to up the week to counter-balance the fact
+ # that with %W that first Monday starts week 1 while with %U that is
+ # week 0 and thus shifts everything by a week
+ if weekday == 0 and first_weekday == 0 and week_of_year_start == 6:
+ week_of_year += 1
+ # If in week 0, then just figure out how many days from Jan 1 to day of
+ # week specified, else calculate by multiplying week of year by 7,
+ # adding in days in week 0, and the number of days from Monday to the
+ # day of the week
+ if week_of_year == 0:
+ julian = 1 + weekday - first_weekday
+ else:
+ days_to_week = preceeding_days + (7 * (week_of_year - 1))
+ julian = 1 + days_to_week + weekday
+ # Cannot pre-calculate datetime_date() since can change in Julian
+ #calculation and thus could have different value for the day of the week
+ #calculation
+ if julian == -1:
+ # Need to add 1 to result since first day of the year is 1, not 0.
+ julian = datetime_date(year, month, day).toordinal() - \
+ datetime_date(year, 1, 1).toordinal() + 1
+ else: # Assume that if they bothered to include Julian day it will
+ #be accurate
+ datetime_result = datetime_date.fromordinal((julian - 1) +\
+ datetime_date(year, 1, 1).toordinal())
+ year = datetime_result.year
+ month = datetime_result.month
+ day = datetime_result.day
+ if weekday == -1:
+ weekday = datetime_date(year, month, day).weekday()
+ return _struct_time(space, [year, month, day,
+ hour, minute, second,
+ weekday, julian, tz])
+
More information about the Pypy-commit
mailing list